
Visit my Gumroad/Ko-fi for exclusive access to all 60+ of my LoRAs! ▼▼▼▼▼
I'll be releasing 1-2 LoRAs on Civit every month, with early access on my stores, and over 60 exclusive models ? Members can get full access to my entire archive plus my private TG for my steamiest content!
-
PLEASE NOTE: The trigger token I trained this on, "bad bunny" is, well, really not good. You will get a lot of bunny ears and strange generations. For an easier-to-use version with much better generations on average, check out my V2 on my links.
This is a LoRA trained on the 1.5 base SD model, at 768px. Please share your SFW results and feedback for any future training improvements.
Recommendations:
-
Trigger token: bad bunny
-
Strength: 0.7-1, I usually start at 0.9
-
Tags:
-
Adjust his hair color/length and facial hair with your desired prompts
-
Adding 'brown eyes' to positive prompt enhances realism
-
Negative prompts: "animal ears, hat, headpiece" if you're getting weird stuff
-
-
I recommend using After Detailer + Hires Fix, or IMG2IMG double upscaling using MultiDiffusion and ControlNet Tile for highly accurate faces
I am not responsible for your use of this resource, which is not for commercial use and is for research purposes only.
描述:
训练词语: bad bunny
名称: diffusiondudes_BadBunny_V1-10.safetensors
大小 (KB): 36983
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success